Intel® Distribution of OpenVINO™ Toolkit
Community assistance about the Intel® Distribution of OpenVINO™ toolkit, OpenCV, and all aspects of computer vision-related on Intel® platforms.

Why use OpenVINO with my TS App?

gilmotta
Beginner
506 Views

I have a working TS app for object identification but I fail to see the benefit of using OpenVINO. I purchased the VPU stick but now I am confused and I need some clarification.

1. If I have an App running on my PC, will it work on any EDGE device or that is the job of OpenVINO?

    for example mini PCs

 

2. Is there a step by step guide on how to convert my TS app to OpenVINO?

 

Thanks for your help.

 

0 Kudos
1 Solution
Munesh_Intel
Moderator
458 Views

Hi Gilson,


OpenVINO toolkit is used to develop and deploy vision-oriented solutions across various Intel platforms, on the cloud or the edge, and is focused on deep learning inference. Please view the video below for introduction to OpenVINO.

What is OpenVINO? | OpenVINO™ toolkit | Ep. 01 | Intel Software


Neural Compute Stick 2 meanwhile is an affordable USB-based development kit that enables testing, tuning and prototyping of deep neural networks directly on devices, without the need of a network or cloud connection. Please view the video below for introduction to Neural Compute Stick 2.

Introducing the Intel Neural Compute Stick 2


For your first question, you need to ensure that your TensorFlow model layers are supported by OpenVINO Model Optimizer and Inference Engine. More information is available at the following pages:


Model Optimizer TensorFlow Supported Operations:

https://docs.openvinotoolkit.org/2021.1/openvino_docs_MO_DG_prepare_model_Supported_Frameworks_Layers.html#tensorflow_supported_operations


Inference Engine Supported Layers for various devices: https://docs.openvinotoolkit.org/2021.1/openvino_docs_IE_DG_supported_plugins_Supported_Devices.html#supported_layers


The typical workflow for deploying a trained deep learning model is given here:

https://docs.openvinotoolkit.org/2021.1/openvino_docs_MO_DG_Deep_Learning_Model_Optimizer_DevGuide.html


For your second question, we only have step-by-step guide for TensorFlow model conversion. More information is available at the following link:

https://docs.openvinotoolkit.org/2021.1/openvino_docs_MO_DG_prepare_model_convert_model_Convert_Model_From_TensorFlow.html


Regards,

Munesh


View solution in original post

0 Kudos
4 Replies
Munesh_Intel
Moderator
496 Views

Hi Gilmotta,


Thanks for reaching out to us. Can you please help to clarify what does 'TS App' stand for? Do you mean TensorFlow ?


Regards,

Munesh


0 Kudos
gilmotta
Beginner
476 Views

Sorry, I wrote TS but I meant TF. Yes, Tensorflow.

0 Kudos
Munesh_Intel
Moderator
459 Views

Hi Gilson,


OpenVINO toolkit is used to develop and deploy vision-oriented solutions across various Intel platforms, on the cloud or the edge, and is focused on deep learning inference. Please view the video below for introduction to OpenVINO.

What is OpenVINO? | OpenVINO™ toolkit | Ep. 01 | Intel Software


Neural Compute Stick 2 meanwhile is an affordable USB-based development kit that enables testing, tuning and prototyping of deep neural networks directly on devices, without the need of a network or cloud connection. Please view the video below for introduction to Neural Compute Stick 2.

Introducing the Intel Neural Compute Stick 2


For your first question, you need to ensure that your TensorFlow model layers are supported by OpenVINO Model Optimizer and Inference Engine. More information is available at the following pages:


Model Optimizer TensorFlow Supported Operations:

https://docs.openvinotoolkit.org/2021.1/openvino_docs_MO_DG_prepare_model_Supported_Frameworks_Layers.html#tensorflow_supported_operations


Inference Engine Supported Layers for various devices: https://docs.openvinotoolkit.org/2021.1/openvino_docs_IE_DG_supported_plugins_Supported_Devices.html#supported_layers


The typical workflow for deploying a trained deep learning model is given here:

https://docs.openvinotoolkit.org/2021.1/openvino_docs_MO_DG_Deep_Learning_Model_Optimizer_DevGuide.html


For your second question, we only have step-by-step guide for TensorFlow model conversion. More information is available at the following link:

https://docs.openvinotoolkit.org/2021.1/openvino_docs_MO_DG_prepare_model_convert_model_Convert_Model_From_TensorFlow.html


Regards,

Munesh


0 Kudos
Munesh_Intel
Moderator
436 Views

Hi Gilson,

 

This thread will no longer be monitored since we have provided relevant information and clarification. If you need any additional information from Intel, please submit a new question.

 

Regards,

Munesh

 

0 Kudos
Reply